Anthropic's text watermark is easy to bypass on several older Claude models

The DecoderNov 4

The headline and the reporting belong to The Decoder. AI Broadsheet shows the headline and a link, without reusing the text or photos unless the publisher allows it. Our standards

Text

Full coverage

How 2 newsrooms are reporting this story.

TechCrunchAnthropic is working on a system to prove AI models’ identity
TechCrunchNov 3

Report an error

Weekly newsletter · free

The Canadian AI Brief

Once a week: what changed in AI, what it means for Canada, and where each fact comes from. Sources named, AI-assisted work labelled.

Anthropic's text watermark is easy to bypass on several older Claude models

Full coverage

The Canadian AI Brief

More in Rights & power

OpenAI is already trying to shape the 2028 election

The Results Are In: Voters Hate Data Centers

Ukraine’s drone strikes spur hasty Russian plans for underground data centers

Finance Minister calls Cohere the “poster child” for government investment

How “reverse game theory” could keep AI agents in check

LifeVal